| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007939343416299472, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015878686832598943, | |
| "eval_loss": 10.346136093139648, | |
| "eval_runtime": 278.8155, | |
| "eval_samples_per_second": 9.512, | |
| "eval_steps_per_second": 4.756, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007939343416299473, | |
| "grad_norm": 14.653383255004883, | |
| "learning_rate": 5e-05, | |
| "loss": 41.5604, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015878686832598945, | |
| "grad_norm": 38.277191162109375, | |
| "learning_rate": 0.0001, | |
| "loss": 38.9418, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015878686832598945, | |
| "eval_loss": 7.547411918640137, | |
| "eval_runtime": 279.9141, | |
| "eval_samples_per_second": 9.474, | |
| "eval_steps_per_second": 4.737, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0023818030248898415, | |
| "grad_norm": 27.24056053161621, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 20.7679, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003175737366519789, | |
| "grad_norm": 48.336856842041016, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.9997, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003175737366519789, | |
| "eval_loss": 0.9895888566970825, | |
| "eval_runtime": 280.8666, | |
| "eval_samples_per_second": 9.442, | |
| "eval_steps_per_second": 4.721, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003969671708149736, | |
| "grad_norm": 50.5829963684082, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.4931, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004763606049779683, | |
| "grad_norm": 45.21467590332031, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5443, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004763606049779683, | |
| "eval_loss": 0.33188173174858093, | |
| "eval_runtime": 280.4106, | |
| "eval_samples_per_second": 9.458, | |
| "eval_steps_per_second": 4.729, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00555754039140963, | |
| "grad_norm": 19.217050552368164, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1656, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006351474733039578, | |
| "grad_norm": 12.236564636230469, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8458, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006351474733039578, | |
| "eval_loss": 0.24062801897525787, | |
| "eval_runtime": 281.0159, | |
| "eval_samples_per_second": 9.437, | |
| "eval_steps_per_second": 4.719, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007145409074669525, | |
| "grad_norm": 22.780681610107422, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8862, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007939343416299472, | |
| "grad_norm": 17.021995544433594, | |
| "learning_rate": 0.0, | |
| "loss": 0.9225, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007939343416299472, | |
| "eval_loss": 0.21980232000350952, | |
| "eval_runtime": 281.0667, | |
| "eval_samples_per_second": 9.435, | |
| "eval_steps_per_second": 4.718, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.571260104572928e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |